CN107403143A - Gait recognition method and electronic equipment - Google Patents
Gait recognition method and electronic equipment Download PDFInfo
- Publication number
- CN107403143A CN107403143A CN201710547836.7A CN201710547836A CN107403143A CN 107403143 A CN107403143 A CN 107403143A CN 201710547836 A CN201710547836 A CN 201710547836A CN 107403143 A CN107403143 A CN 107403143A
- Authority
- CN
- China
- Prior art keywords
- gait
- parameter
- cycle
- destination object
- electronic equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005021 gait Effects 0.000 title claims abstract description 354
- 238000000034 method Methods 0.000 title claims abstract description 55
- 206010017577 Gait disturbance Diseases 0.000 claims abstract description 56
- 230000001133 acceleration Effects 0.000 claims description 11
- 230000027455 binding Effects 0.000 claims description 11
- 238000009739 binding Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 241000208340 Araliaceae Species 0.000 claims description 5
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 5
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 5
- 235000008434 ginseng Nutrition 0.000 claims description 5
- 201000010099 disease Diseases 0.000 description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 18
- 238000003860 storage Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 7
- 210000002414 leg Anatomy 0.000 description 7
- 230000036541 health Effects 0.000 description 5
- 230000001771 impaired effect Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 208000011644 Neurologic Gait disease Diseases 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000007170 pathology Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 206010017585 Gait spastic Diseases 0.000 description 1
- 241000489861 Maximus Species 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 208000018737 Parkinson disease Diseases 0.000 description 1
- 206010056242 Parkinsonian gait Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 210000001624 hip Anatomy 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 230000006742 locomotor activity Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 208000018360 neuromuscular disease Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 210000003371 toe Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/76—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries based on eigen-space representations, e.g. from pose or different illumination conditions; Shape manifolds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
Abstract
The embodiment of the invention discloses a gait recognition method and electronic equipment, wherein the method comprises the following steps: acquiring gait parameters of a target object; extracting gait feature information of the gait parameters according to the gait parameters; matching the gait feature information with an abnormal gait model stored in a gait database to obtain a matching rate; and if the matching rate reaches a preset threshold value, identifying that the current gait of the target object is abnormal gait. By implementing the embodiment of the invention, the accuracy of gait recognition can be improved, and the probability of misjudgment is reduced.
Description
Technical field
The present invention relates to technical field of electronic equipment, and in particular to a kind of gait recognition method and electronic equipment.
Background technology
Gait refers to posture during human locomotion, and human body makes body by a series of continuously actives of hip, knee, ankle, toes etc.
The process that body moves along certain orientation.Normal gait typically has stability, periodicity, rhythmicity, directionality and coordination
The features such as property.However, gait may be all influenceed when human body has disease or any link is lacked of proper care, so as to form pathology gait.
Gait analysis is a kind of technology for being used for analyzing and assessing human body locomotor activity, and body gait can be found in time by analysis
Abnormal, (such as brain paralysis, Parkinson's disease and neuromuscular disease) is widely used in terms of human pathologies' situation at present.However,
The assessment result of gait analysis technology depends primarily on the judgement of observer, i.e. the composition of human factor is larger, thus holds very much
Easily judge by accident, so that the degree of accuracy of gait analysis is low.
The content of the invention
The embodiment of the invention discloses a kind of gait recognition method and electronic equipment, it is possible to increase Gait Recognition it is accurate
Degree.
First aspect of the embodiment of the present invention discloses a kind of gait recognition method, and methods described is applied in electronic equipment, institute
The method of stating includes:
Obtain the gait parameter of destination object;
According to the gait parameter, the gait feature information of the gait parameter is extracted;
The gait feature information is matched with the abnormal gait model stored in gait data storehouse, to be matched
Rate;
If the matching rate reaches predetermined threshold value, the current gait for identifying the destination object is abnormal gait.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the step for obtaining destination object
Before state parameter, methods described also includes:
Establish the binding relationship of the electronic equipment and at least one external equipment;
After the current gait for identifying the destination object is abnormal gait, methods described also includes:
Warning message is sent at least one external equipment, the warning message includes being used for warning the target pair
The information of the abnormal gait of elephant.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the gait ginseng of the destination object
Number includes at least one of acceleration, step-length, stride, step width, cadence, leg speed and sufficient angle when the destination object is walked
Information parameter.
It is described according to the gait parameter as an alternative embodiment, in first aspect of the embodiment of the present invention,
The gait feature information of the gait parameter is extracted, including:
The gait parameter is parsed, step of the destination object in a gait cycle is determined from the gait parameter
State parameter, to obtain cycle gait parameter;
Gait feature information is extracted from the cycle gait parameter.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the parsing gait parameter,
Gait parameter of the destination object in a gait cycle is determined from the gait parameter, to obtain cycle gait ginseng
Number, including:
The gait parameter is pre-processed, to obtain pretreated gait parameter;
Gait cycle is carried out to the pretreated gait parameter using the mode of local maximum and local minimum
Division, to obtain the gait parameter in each gait cycle;
The gait parameter chosen in gait parameter out of described each gait cycle in one of gait cycle is made
For cycle gait parameter.
Second aspect of the embodiment of the present invention discloses a kind of electronic equipment, including:
Acquiring unit, for obtaining the gait parameter of destination object;
Extraction unit, for according to the gait parameter, extracting the gait feature information of the gait parameter;
Matching unit, the abnormal gait model for that will store in the gait feature information and gait data storehouse are carried out
Match somebody with somebody, to obtain matching rate;
Recognition unit, when the matching rate for being obtained when the matching unit reaches predetermined threshold value, identify described
The current gait of destination object is abnormal gait.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the electronic equipment also includes:
Unit is established, for before the gait parameter of acquiring unit acquisition destination object, establishing the electronics and setting
The standby binding relationship with least one external equipment;
Transmitting element, for identified in the recognition unit the current gait of the destination object for abnormal gait it
Afterwards, warning message is sent at least one external equipment, the warning message includes being used for warning the destination object
The information of abnormal gait.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the gait ginseng of the destination object
Number includes at least one of acceleration, step-length, stride, step width, cadence, leg speed and sufficient angle when the destination object is walked
Information parameter.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the extraction unit includes:
Determination subelement, for parsing the gait parameter, determine the destination object one from the gait parameter
Gait parameter in individual gait cycle, to obtain cycle gait parameter;
Subelement is extracted, for extracting gait feature information from the cycle gait parameter.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the determination subelement is specifically used
In being pre-processed the gait parameter to obtain pretreated gait parameter, local maximum and local minimum are utilized
Mode the division of gait cycle is carried out to the pretreated gait parameter, to obtain the gait in each gait cycle
Parameter, and the gait parameter conduct in one of gait cycle is chosen in the gait parameter out of described each gait cycle
Cycle gait parameter.
The third aspect of the embodiment of the present invention discloses a kind of electronic equipment, including:
It is stored with the memory of executable program code;
The processor coupled with the memory;
The processor calls the executable program code stored in the memory, performs the embodiment of the present invention the
The gait recognition method disclosed in one side.
Fourth aspect of the embodiment of the present invention discloses a kind of computer-readable recording medium, and it stores computer program, wherein,
The computer program causes computer to perform the gait recognition method disclosed in first aspect of the embodiment of the present invention.
Compared with prior art, the embodiment of the present invention has the advantages that:
In the embodiment of the present invention, when using electronic equipment to identify the gait of destination object, electronics can be first passed through and set
The gait parameter of standby collection destination object, further according to the gait parameter, therefrom extracts corresponding gait feature information;In this base
On plinth, the gait feature information extracted can be matched with the abnormal gait model stored in gait data storehouse, to obtain
Obtain matching rate;Further, by the matching rate compared with predetermined threshold value, if the matching rate is more than or equal to default threshold
Value, then the current gait for identifying the destination object is abnormal gait;If the matching rate is less than predetermined threshold value, this is identified
The current gait of destination object is non-abnormal gait, as normal gait.By implementing the embodiment of the present invention, without excessive artificial
The interference of factor, but the characteristic information of the gait parameter collected is compared with the abnormal gait model pre-established,
To obtain final Gait Recognition result.So as to effectively improve the degree of accuracy of Gait Recognition, and reduce the probability of erroneous judgement.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it will use below required in embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of schematic flow sheet of gait recognition method disclosed in the embodiment of the present invention;
Fig. 2 is the schematic diagram of several abnormal gaits disclosed in the embodiment of the present invention;
Fig. 3 is the schematic flow sheet of another gait recognition method disclosed in the embodiment of the present invention;
Fig. 4 is the schematic diagram in each composition stage of a gait cycle disclosed in the embodiment of the present invention;
Fig. 5 is the structural representation of a kind of electronic equipment disclosed in the embodiment of the present invention;
Fig. 6 is the structural representation of another electronic equipment disclosed in the embodiment of the present invention;
Fig. 7 is the structural representation of another electronic equipment disclosed in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example is applied, belongs to the scope of protection of the invention.
It should be noted that term " comprising " and " having " and their any changes in the embodiment of the present invention and accompanying drawing
Shape, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method, system, product or
The step of equipment is not limited to list or unit, but alternatively also include the step of not listing or unit, or it is optional
Ground is also included for the intrinsic other steps of these processes, method, product or equipment or unit.
The embodiment of the invention discloses a kind of gait recognition method and electronic equipment, it is possible to increase Gait Recognition it is accurate
Degree, reduce the probability of erroneous judgement.It is described in detail individually below.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of schematic flow sheet of gait recognition method disclosed in the embodiment of the present invention.Wherein, scheme
Gait recognition method described by 1 goes for cell phone, tablet personal computer, personal digital assistant (Personal
Digital Assistant, PDA), Intelligent worn device (such as intelligent watch, Intelligent bracelet, intelligent necklace), mobile interchange
Each class of electronic devices, the embodiment of the present invention such as net equipment (Mobile Internet Device, MID) are not construed as limiting.Such as Fig. 1 institutes
Show, the gait recognition method may comprise steps of:
101st, electronic equipment obtains the gait parameter of destination object.
In the embodiment of the present invention, destination object can be human or animal.Electronic equipment can be provided with gait detection application,
Gait detection application can be third-party application software that electronic equipment carries or installation.When target to be detected
During the gait parameter of object, the detection application of the gait in electronic equipment can be opened to gather destination object when walking in real time
Gait parameter.Wherein, for electronic equipment when gathering the gait parameter of destination object, destination object can carry with electronics to set
It is standby, such as electronic equipment taken, is placed in pocket, or electronic equipment is worn.It is of course also possible to it is target pair
As establishing wired with electronic equipment or wireless type is connected, electronic equipment need not be now carried with.
In the embodiment of the present invention, the gait parameter of destination object can include but is not limited to acceleration when destination object is walked
At least one of degree, step-length, stride, step width, cadence, leg speed and sufficient angle etc. information parameter.It can be configured in electronic equipment
There are the acceleration transducer for gathering the acceleration parameter of destination object, such as 3-axis acceleration sensor, can also configure
There is special chip or circuit for gathering the parameters such as step-length, stride, step width, cadence, leg speed and sufficient angle etc..
102nd, electronic equipment extracts the gait feature information of the gait parameter according to the gait parameter.
In the embodiment of the present invention, the gait parameter of electronic equipment collection can be destination object when walking in a period of time
Parameters index, the parameters in this period of time can be parsed, included so as to extracting parameters
Characteristic information.For example, analyzing the acceleration information in this period of time, its characteristic information is extracted;Or to this
Cadence parameter in a period of time is analyzed, and extracts the characteristic information etc. in cadence parameter.
103rd, electronic equipment is matched the gait feature information with the abnormal gait model stored in gait data storehouse,
To obtain matching rate.
Wherein, abnormal gait model had both been stored with gait data storehouse, normal gait model can also be stored.Actually should
In, abnormal gait model and/or normal gait model can be pre-established.Specifically, first gather substantial amounts of abnormal gait ginseng
Number and/normal gait parameter, and model training operation is carried out after being pre-processed to these parameters, exception can be obtained after the completion of training
Gait pattern and/or normal gait model, and be saved in gait data storehouse.
In the embodiment of the present invention, gait data storehouse can be stored in electronic equipment local terminal, can also store it in other
Equipment or server end.Optionally, the exception that step 103 electronic equipment will store in the gait feature information and gait data storehouse
Gait pattern is matched, and may comprise steps of with obtaining the embodiment of matching rate:
11) abnormal gait that electronic equipment will store in the gait data storehouse of the gait feature information and electronic equipment itself
Model is matched, to obtain matching rate;Or
12) electronic equipment walks the gait feature information with the exception stored from the gait data storehouse that server end obtains
States model is matched, to obtain matching rate.
104th, electronic equipment judges whether the matching rate reaches predetermined threshold value, if it is, performing step 105;If not,
Then perform step 106.
105th, electronic equipment identifies that the current gait of the destination object is abnormal gait.
106th, electronic equipment identifies that the current gait of the destination object is normal gait.
In the embodiment of the present invention, after the matching rate between gait feature information and abnormal gait model is obtained, it can incite somebody to action
The matching rate, when the matching rate is more than or equal to predetermined threshold value, shows the step compared with the predetermined threshold value being previously stored
The matching degree of state characteristic information and abnormal gait model is high, and it is different that can now determine gait when destination object is currently walked
Normal gait.Conversely, when the matching rate is less than predetermined threshold value, show the matching degree of the gait feature information and abnormal gait model
Low, it is normal gait that can now determine gait when destination object is currently walked.
Wherein, the parameter of normal gait is generally step-length 50-80cm, and stride is usually twice of step-length, and step width is (with heel
Midpoint is measurement point) it is 4.5-11.5cm, sufficient angle is about 6.75 °, and cadence is about that 95-125 steps/minute, (east male's cadence was about
For 112.2 ± 8.9 steps/minute, women is about 123.4 ± 8.0 steps/minute), leg speed is about 65-95 ms/min.And exception walks
The species of state has a variety of situations, as shown in Fig. 2 abnormal gait can include but is not limited to hemiplegic gait, paraparetic gait, gluteus maximus
Gait, glutaeus medius gait, festinating gait, reeling gait, tibialis anterior gait etc..Wherein, the parameter of abnormal gait and normal step
The parameter of state is compared, and has larger difference.
As an alternative embodiment, after execution of step 105, the method described by Fig. 1 can also include
Following steps:
13) electronic equipment output warning message, the warning message include the letter for being used for warning the abnormal gait of destination object
Breath.
In this embodiment, when identifying that destination object is currently at the state of abnormal gait, electronic equipment can be with
Warning message is exported in a manner of word and/or voice etc., it is abnormal to prompt the current gait of the destination object to exist.By implementing to be somebody's turn to do
Embodiment, when there is abnormal gait, early warning can be carried out to destination object itself in time, reminded, body can be found in advance
Existing disease is simultaneously treated in time, and then can be reduced because disease fails to find in advance, causes disease further to deepen or body
The risk and probability to go to bits.
As an alternative embodiment, before step 101 is performed, the method described by Fig. 1 can also include with
Lower step:
14) binding relationship of electronic equipment and at least one external equipment is established;
Correspondingly, after execution of step 105, the method described by Fig. 1 can also comprise the following steps:
15) warning message is sent to above-mentioned at least one external equipment, the warning message includes being used for warning destination object
Abnormal gait information.
In this embodiment, can be by the electronic equipment of destination object before the gait parameter of detected target object
Bound with other external equipments, such as the cell phone apparatus of the electronic equipment of destination object and household is bound.Here
Binding can be understood as establishing the annexation of wired and/or wireless type.Specifically, it can be set in the electronics of destination object
The bindings with other external equipments are carried out in gait detection application in standby, can according to the actual requirements add or delete certain
The binding of individual external equipment and the electronic equipment.When identifying that destination object is currently at the state of abnormal gait, electronics is set
It is standby to push warning message to the part or all of external equipment of binding, to inform owner's current goal pair of external equipment
The gait of elephant exists abnormal., can be in time to the household of destination object when there is abnormal gait by implementing the embodiment
Or caregiver carries out early warning, reminded, and can find disease existing for the body of destination object in advance and treat in time, and then can drop
Low target object causes disease is further deepened or health is impaired risk and probability because disease fails to find in advance.
In the method described by Fig. 1, when using electronic equipment to identify the gait of destination object, electricity can be first passed through
The gait parameter of sub- equipment collection destination object, further according to the gait parameter, therefrom extracts corresponding gait feature information;
On the basis of this, the gait feature information extracted can be matched with the abnormal gait model stored in gait data storehouse,
To obtain matching rate;Further, by the matching rate compared with predetermined threshold value, preset if the matching rate is more than or equal to
Threshold value, the then current gait for identifying the destination object are abnormal gait;If the matching rate is less than predetermined threshold value, identify
The current gait of the destination object is non-abnormal gait, as normal gait.By implementing the embodiment of the present invention, without excessive people
For the interference of factor, but the characteristic information of the gait parameter collected is compared with the abnormal gait model pre-established
It is right, to obtain final Gait Recognition result.So as to effectively improve the degree of accuracy of Gait Recognition, and reduce the general of erroneous judgement
Rate.In addition, hiding disease can be found in advance, so can reduce disease is further deepened or health is impaired risk and
Probability.
Embodiment two
Referring to Fig. 3, Fig. 3 is the schematic flow sheet of another gait recognition method disclosed in the embodiment of the present invention.Wherein,
The gait recognition method can apply in electronic equipment.As shown in figure 3, the gait recognition method may comprise steps of:
301st, electronic equipment obtains the gait parameter of destination object.
Wherein, the gait parameter of destination object can include but is not limited to destination object walking when acceleration, step-length, step
At least one of width, step width, cadence, leg speed and sufficient angle etc. information parameter.
302nd, electronic equipment parses the gait parameter, determines destination object in a gait cycle from the gait parameter
Gait parameter, to obtain cycle gait parameter.
In the embodiment of the present invention, due to human or animal when walking, its gait is in periodic.Therefore, for collection
The gait parameter in a period of time arrived, each gait cycle can be marked off according to the regularity of gait parameter, by one
Gait parameter in individual gait cycle, which carries out analyzing and processing, can parse the gait situation of destination object.
As an alternative embodiment, step 302 electronic equipment parses the gait parameter, from the gait parameter really
Set the goal gait parameter of the object in a gait cycle, can be included with obtaining the embodiment of cycle gait parameter
Following steps:
31) gait parameter is pre-processed, to obtain pretreated gait parameter;
32) gait cycle is carried out to pretreated gait parameter using the mode of local maximum and local minimum
Division, to obtain the gait parameter in each gait cycle;
33) gait parameter in one of gait cycle is chosen in the gait parameter out of above-mentioned each gait cycle
As cycle gait parameter.
In this embodiment, can be first to this after the gait parameter when electronic equipment collects destination object walking
Gait parameter is pre-processed, specifically, gait parameter, which is pre-processed, can include carrying out the gait parameter collected
Correction, then carries out denoising again, wherein, the mode of denoising may be referred to existing noise-removed technology, such as utilize FIR
Two kinds of denoising modes of (Finite Impulse Response, finite impulse response (FIR)) linear filter and wavelet threshold are to gait
Parameter carries out denoising, obtains the cyclical signal of relative smooth.It is possible to further utilize the sampling number in each cycle
Pretreated gait parameter is carried out at the division of gait cycle with the mode that local maximum and local minimum are combined
Reason, to mark off the gait parameter in each gait cycle, and then can be from the gait parameter in above-mentioned each gait cycle
Select the gait parameter in a gait cycle.Wherein it is possible to it is to randomly select or choose the step specified in the cycle
State parameter, such as a cycle, second period, last cycle.
The gait cycle of people when walking can be defined as when walking side heel contact to the parapodum with
The process to land again, generally represented with second time (s), the gait cycle being typically grown up is about 1~1.32s or so.Such as Fig. 4
Shown in citing, a complete gait cycle can be divided into two stages, be " driving phase (stance respectively
Phase) " and " recovery phase (swing phase) ", and seven parts can be further divided into again.That is, " driving phase " can be with
Including reaction of contacting to earth, contact to earth first, support mid-term and support latter stage totally four parts, wherein, contacting to earth first, it is single to be used as
An only stage is without being included in driving phase." recovery phase " can include swinging early stage, swing mid-term and swinging latter stage
Totally three parts.Gait parameter in one gait cycle includes the respective parameter in above-mentioned seven parts, the parameter of each section
It is respectively provided with respective feature.
303rd, electronic equipment extracts gait feature information from the cycle gait parameter.
In the embodiment of the present invention, before gait feature information is extracted, normalizing first can be carried out to the cycle gait parameter
Change is handled, specifically, amplitude normalization and time normalization processing are carried out to the cycle gait parameter, it is exhausted in parameter to eliminate
To measuring influence during to Gait Recognition.Optionally, step 303 electronic equipment extracts gait feature from the cycle gait parameter
The embodiment of information can include:Cycle gait parameter dimension is carried out by interpolation method and periodic sampling mode
It is regular, wavelet transformation is carried out to cycle gait parameter as wavelet basis function using the single order derived function of Gaussian function afterwards, led to
The zero crossing crossed after finding out wavelet transformation can extract the extreme point in cycle gait parameter, so that it is determined that going out gait feature letter
Breath.
304th, electronic equipment is matched the gait feature information with the abnormal gait model stored in gait data storehouse,
To obtain matching rate.
In the embodiment of the present invention, specific embodiment party that the gait feature information of extraction is matched with abnormal gait model
Formula can be:Utilize dynamic time warping (Dynamic Time Warping, DTW) algorithm, garbled-reception rate and False Rejects
Rate asks for the threshold value of gait feature information, and is entered using multi-level judgement system and the abnormal gait model in gait data storehouse
Row matching, so as to obtain matching rate.
305th, electronic equipment judges whether the matching rate reaches predetermined threshold value, if it is, performing step 306;If not,
Then perform step 307.
306th, electronic equipment identifies that the current gait of the destination object is abnormal gait.
307th, electronic equipment identifies that the current gait of the destination object is normal gait.
As an alternative embodiment, electronic equipment after Gait Recognition terminates, can export warning message automatically,
To prompt destination object current gait situation.In addition, when binding has other external equipments on electronic equipment, can also be to tying up
Fixed external equipment push warning message, to inform the health status of the household of destination object or caregiver's current target object,
To have found that it is likely that existing health problem in time.
In actual applications, can be by the gait recognition method described in above-described embodiment come detected target object
Gait whether there is unusual condition, to find hiding disease in advance;This method can also be used in monitoring objective object rehabilitation
Stage, by analyzing the gait of destination object, come monitoring objective object, whether the state of an illness is eased or the scene such as aggravation.
Wherein, the method described by implementing Fig. 3, without the interference of excessive human factor, but the gait collected is joined
Several characteristic informations is compared with the abnormal gait model pre-established, to obtain final Gait Recognition result.So as to
The degree of accuracy of Gait Recognition is enough effectively improved, and reduces the probability of erroneous judgement.
In addition, the method described by implementing Fig. 3, can be in time to target when identifying the abnormal gait of destination object
The household of object or caregiver carry out early warning, reminded, and can find disease existing for the body of destination object in advance and treat in time,
And then destination object can be reduced because disease fails to find in advance, cause the risk that disease is further deepened or health is impaired
And probability.
Embodiment three
Referring to Fig. 5, Fig. 5 is the structural representation of a kind of electronic equipment disclosed in the embodiment of the present invention.Wherein, the electronics
Equipment can be used for performing the gait recognition method described in above-described embodiment.As shown in figure 5, the electronic equipment can wrap
Include:
Acquiring unit 501, for obtaining the gait parameter of destination object.
Wherein, the gait parameter of destination object can include but is not limited to destination object walking when acceleration, step-length, step
At least one of the information such as width, step width, cadence, leg speed and sufficient angle information parameter.
Extraction unit 502, for according to the gait parameter, extracting the gait feature information of the gait parameter.
Matching unit 503, the abnormal gait model for will be stored in the gait feature information and gait data storehouse are carried out
Matching, to obtain matching rate.
Specifically, matching unit 503 can be used for the gait data storehouse by the gait feature information and electronic equipment itself
The abnormal gait model of middle storage is matched, to obtain matching rate;Or matching unit 503 can be used for gait spy
Reference breath is matched with the abnormal gait model stored in the gait data storehouse obtained from server end, to obtain matching rate.
Recognition unit 504, when the matching rate for being obtained when matching unit 503 reaches predetermined threshold value, identify the mesh
The current gait for marking object is abnormal gait.
Optionally, recognition unit 504, it can be also used for the not up to default threshold of the matching rate obtained when matching unit 503
During value, the current gait for identifying the destination object is normal gait.
Also referring to Fig. 6, Fig. 6 is the structural representation of another electronic equipment disclosed in the embodiment of the present invention, can be with
For performing the gait recognition method described in above-described embodiment.Wherein, the electronic equipment shown in Fig. 6 is shown in Fig. 5
Further optimize what is obtained on the basis of electronic equipment.Compared with the electronic equipment shown in Fig. 5, the electronics shown in Fig. 6 is set
It is standby to include:
Unit 505 is established, for before the gait parameter of the acquisition destination object of acquiring unit 501, establishing the electronics and setting
The standby binding relationship with least one external equipment;
Transmitting element 506, after the current gait of destination object is identified in recognition unit 504 as abnormal gait,
Warning message is sent to above-mentioned at least one external equipment, the warning message can include being used for warning the gait of destination object different
Normal information.
As an alternative embodiment, extraction unit 502 may further include in electronic equipment shown in Fig. 6:
Determination subelement 5021, for parsing the gait parameter, determine destination object in a step from the gait parameter
Gait parameter in the state cycle, to obtain cycle gait parameter;
Subelement 5022 is extracted, for extracting gait feature information from the cycle gait parameter.
As an alternative embodiment, determination subelement 5021 specifically can be used for locating the gait parameter in advance
Reason is joined with obtaining pretreated gait parameter using the mode of local maximum and local minimum to pretreated gait
Number carries out the division of gait cycle, to obtain the gait parameter in each gait cycle, and out of each gait cycle
The gait parameter in one of gait cycle is chosen in gait parameter as cycle gait parameter.
Wherein, implement the electronic equipment described by Fig. 5 and Fig. 6, without the interference of excessive human factor, but will collect
The characteristic information of gait parameter be compared with the abnormal gait model pre-established, to obtain final Gait Recognition knot
Fruit.So as to effectively improve the degree of accuracy of Gait Recognition, and reduce the probability of erroneous judgement.
In addition, implement Fig. 5 and Fig. 6 described by electronic equipment, when identifying the abnormal gait of destination object, can and
When to the household of destination object or caregiver carry out early warning, remind, disease existing for the body of destination object can be found in advance simultaneously
Treatment in time, and then can reduce destination object because disease fails to find in advance, cause disease further to deepen or health
Impaired risk and probability.
Example IV
Referring to Fig. 7, Fig. 7 is the structural representation of another electronic equipment disclosed in the embodiment of the present invention.Such as Fig. 7 institutes
Show, the electronic equipment can include:
It is stored with the memory 701 of executable program code;
The processor 702 coupled with memory 701;
Wherein, processor 702 calls the executable program code stored in memory 701, performs described by Fig. 1 or Fig. 3
Method.
In addition, implementing the electronic equipment described by Fig. 7, the degree of accuracy for improving Gait Recognition is can aid in, and reduce mistake
The probability sentenced;In addition, hiding disease can be found in advance, and then it can reduce that disease is further deepened or health is impaired
Risk and probability.
The embodiment of the present invention discloses a kind of computer-readable recording medium, and it stores computer program, wherein, the computer
Program causes computer to perform the method described by Fig. 1 or Fig. 3.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
To instruct the hardware of correlation to complete by program, the program can be stored in a computer-readable recording medium, storage
Medium include read-only storage (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only storage (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only storage
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), read-only optical disc (Compact
Disc Read-Only Memory, CD-ROM) or other disk storages, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of data storage.
A kind of gait recognition method and electronic equipment disclosed in the embodiment of the present invention are described in detail above, herein
In apply specific case to the present invention principle and embodiment be set forth, the explanation of above example is only intended to help
Assistant solves the method and its core concept of the present invention;Meanwhile for those of ordinary skill in the art, the think of according to the present invention
Think, in specific embodiments and applications there will be changes, in summary, this specification content should not be construed as pair
The limitation of the present invention.
Claims (12)
1. a kind of gait recognition method, it is characterised in that methods described is applied in electronic equipment, and methods described includes:
Obtain the gait parameter of destination object;
According to the gait parameter, the gait feature information of the gait parameter is extracted;
The gait feature information is matched with the abnormal gait model stored in gait data storehouse, to obtain matching rate;
If the matching rate reaches predetermined threshold value, the current gait for identifying the destination object is abnormal gait.
2. gait recognition method according to claim 1, it is characterised in that it is described obtain destination object gait parameter it
Before, methods described also includes:
Establish the binding relationship of the electronic equipment and at least one external equipment;
After the current gait for identifying the destination object is abnormal gait, methods described also includes:
Warning message is sent at least one external equipment, the warning message includes being used for warning the destination object
The information of abnormal gait.
3. gait recognition method according to claim 1, it is characterised in that the gait parameter of the destination object includes institute
At least one of acceleration, step-length, stride, step width, cadence, leg speed and sufficient angle when stating destination object walking information is joined
Number.
4. according to the gait recognition method any one of claim 1-3, it is characterised in that described to be joined according to the gait
Number, the gait feature information of the gait parameter is extracted, including:
The gait parameter is parsed, gait ginseng of the destination object in a gait cycle is determined from the gait parameter
Number, to obtain cycle gait parameter;
Gait feature information is extracted from the cycle gait parameter.
5. gait recognition method according to claim 4, it is characterised in that the parsing gait parameter, from described
Gait parameter of the destination object in a gait cycle is determined in gait parameter, to obtain cycle gait parameter, including:
The gait parameter is pre-processed, to obtain pretreated gait parameter;
Gait cycle is carried out using the mode of local maximum and local minimum to the pretreated gait parameter to draw
Point, to obtain the gait parameter in each gait cycle;
The gait parameter in one of gait cycle is chosen in gait parameter out of described each gait cycle as week
Phase gait parameter.
6. a kind of electronic equipment, it is characterised in that including:
Acquiring unit, for obtaining the gait parameter of destination object;
Extraction unit, for according to the gait parameter, extracting the gait feature information of the gait parameter;
Matching unit, for the gait feature information to be matched with the abnormal gait model stored in gait data storehouse,
To obtain matching rate;
Recognition unit, when the matching rate for being obtained when the matching unit reaches predetermined threshold value, identify the target
The current gait of object is abnormal gait.
7. electronic equipment according to claim 6, it is characterised in that also include:
Establish unit, for the acquiring unit obtain destination object gait parameter before, establish the electronic equipment with
The binding relationship of at least one external equipment;
Transmitting element, after the current gait of the destination object is identified in the recognition unit as abnormal gait, to
At least one external equipment sends warning message, and the warning message includes being used for warning the gait of the destination object different
Normal information.
8. electronic equipment according to claim 6, it is characterised in that the gait parameter of the destination object includes the mesh
Mark at least one of acceleration, step-length, stride, step width, cadence, leg speed and the sufficient angle when object is walked information parameter.
9. according to the electronic equipment any one of claim 6-8, it is characterised in that the extraction unit includes:
Determination subelement, for parsing the gait parameter, determine the destination object in a step from the gait parameter
Gait parameter in the state cycle, to obtain cycle gait parameter;
Subelement is extracted, for extracting gait feature information from the cycle gait parameter.
10. electronic equipment according to claim 9, it is characterised in that the determination subelement is specifically used for the step
State parameter is pre-processed to obtain pretreated gait parameter, using the mode of local maximum and local minimum to institute
The division that pretreated gait parameter carries out gait cycle is stated, to obtain the gait parameter in each gait cycle, and from
The gait parameter in one of gait cycle is chosen in gait parameter in each described gait cycle as cycle gait
Parameter.
11. a kind of electronic equipment, it is characterised in that including:
It is stored with the memory of executable program code;
The processor coupled with the memory;
The processor calls the executable program code stored in the memory, and perform claim requires any one of 1-5
Described method.
A kind of 12. computer-readable recording medium, it is characterised in that it stores computer program, wherein, the computer program
So that computer perform claim requires the method described in any one of 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710547836.7A CN107403143A (en) | 2017-07-06 | 2017-07-06 | Gait recognition method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710547836.7A CN107403143A (en) | 2017-07-06 | 2017-07-06 | Gait recognition method and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107403143A true CN107403143A (en) | 2017-11-28 |
Family
ID=60404867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710547836.7A Pending CN107403143A (en) | 2017-07-06 | 2017-07-06 | Gait recognition method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107403143A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108600707A (en) * | 2018-06-19 | 2018-09-28 | 华为技术有限公司 | A kind of monitoring method, recognition methods, relevant apparatus and system |
CN110210392A (en) * | 2019-05-31 | 2019-09-06 | 吉林化工学院 | A kind of Gait Recognition device based on probability theory |
CN110874910A (en) * | 2018-08-31 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Road surface alarm method, device, electronic equipment and readable storage medium |
CN111197446A (en) * | 2018-11-20 | 2020-05-26 | 宝沃汽车(中国)有限公司 | Method and device for opening trunk, storage medium and vehicle |
CN111242079A (en) * | 2020-01-20 | 2020-06-05 | 深圳市丞辉威世智能科技有限公司 | Gait detection fusion method, device, equipment and readable storage medium |
CN112906457A (en) * | 2021-01-06 | 2021-06-04 | 南昌大学 | Walking gait signal preprocessing method based on mobile phone acceleration sensor |
TWI788721B (en) * | 2018-07-17 | 2023-01-01 | 長庚大學 | Walking assist device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104091177A (en) * | 2014-06-30 | 2014-10-08 | 华南理工大学 | Abnormal gait detection method based on determined learning theory |
CN105335696A (en) * | 2015-08-26 | 2016-02-17 | 湖南信息职业技术学院 | 3D abnormal gait behavior detection and identification based intelligent elderly assistance robot and realization method |
CN105740621A (en) * | 2016-01-29 | 2016-07-06 | 江阴中科今朝科技有限公司 | Moving monitoring and intelligent aged nursing health cloud platform of human body behavior data |
CN106175778A (en) * | 2016-07-04 | 2016-12-07 | 中国科学院计算技术研究所 | A kind of method setting up gait data collection and gait analysis method |
CN106344031A (en) * | 2016-08-29 | 2017-01-25 | 常州市钱璟康复股份有限公司 | Sound feedback-based gait training and estimating system |
CN106361544A (en) * | 2015-07-23 | 2017-02-01 | 三星电子株式会社 | Walking assistance method and device for executing the same |
CN106778546A (en) * | 2016-11-29 | 2017-05-31 | 聚鑫智能科技(武汉)股份有限公司 | A kind of visual identity method and system based on visible ray and non-visible light |
-
2017
- 2017-07-06 CN CN201710547836.7A patent/CN107403143A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104091177A (en) * | 2014-06-30 | 2014-10-08 | 华南理工大学 | Abnormal gait detection method based on determined learning theory |
CN106361544A (en) * | 2015-07-23 | 2017-02-01 | 三星电子株式会社 | Walking assistance method and device for executing the same |
CN105335696A (en) * | 2015-08-26 | 2016-02-17 | 湖南信息职业技术学院 | 3D abnormal gait behavior detection and identification based intelligent elderly assistance robot and realization method |
CN105740621A (en) * | 2016-01-29 | 2016-07-06 | 江阴中科今朝科技有限公司 | Moving monitoring and intelligent aged nursing health cloud platform of human body behavior data |
CN106175778A (en) * | 2016-07-04 | 2016-12-07 | 中国科学院计算技术研究所 | A kind of method setting up gait data collection and gait analysis method |
CN106344031A (en) * | 2016-08-29 | 2017-01-25 | 常州市钱璟康复股份有限公司 | Sound feedback-based gait training and estimating system |
CN106778546A (en) * | 2016-11-29 | 2017-05-31 | 聚鑫智能科技(武汉)股份有限公司 | A kind of visual identity method and system based on visible ray and non-visible light |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108600707A (en) * | 2018-06-19 | 2018-09-28 | 华为技术有限公司 | A kind of monitoring method, recognition methods, relevant apparatus and system |
TWI788721B (en) * | 2018-07-17 | 2023-01-01 | 長庚大學 | Walking assist device |
CN110874910A (en) * | 2018-08-31 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Road surface alarm method, device, electronic equipment and readable storage medium |
CN110874910B (en) * | 2018-08-31 | 2021-03-23 | 杭州海康威视数字技术股份有限公司 | Road surface alarm method, device, electronic equipment and readable storage medium |
CN111197446A (en) * | 2018-11-20 | 2020-05-26 | 宝沃汽车(中国)有限公司 | Method and device for opening trunk, storage medium and vehicle |
CN110210392A (en) * | 2019-05-31 | 2019-09-06 | 吉林化工学院 | A kind of Gait Recognition device based on probability theory |
CN110210392B (en) * | 2019-05-31 | 2022-12-09 | 吉林化工学院 | Gait recognition device based on probability theory |
CN111242079A (en) * | 2020-01-20 | 2020-06-05 | 深圳市丞辉威世智能科技有限公司 | Gait detection fusion method, device, equipment and readable storage medium |
CN111242079B (en) * | 2020-01-20 | 2023-10-27 | 深圳市丞辉威世智能科技有限公司 | Gait detection fusion method, device, equipment and readable storage medium |
CN112906457A (en) * | 2021-01-06 | 2021-06-04 | 南昌大学 | Walking gait signal preprocessing method based on mobile phone acceleration sensor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107403143A (en) | Gait recognition method and electronic equipment | |
CN105902257B (en) | Sleep state analysis method and device, intelligent wearable device | |
CN106228200B (en) | Action identification method independent of action information acquisition equipment | |
US10537403B2 (en) | Passive RFID based health data monitor | |
US11766182B2 (en) | Systems and methods for real-time signal processing and fitting | |
KR102008196B1 (en) | Apparatus for generating of Potassium level determination model using ECG and method thereof | |
CN105205464A (en) | Fingerprint identification method, fingerprint identification device and terminal | |
CN109363659B (en) | Heart rate monitoring method and device based on deep learning and storage medium | |
US20140247145A1 (en) | Methods using activity manager for monitoring user activity | |
US20140247156A1 (en) | User or patient monitoring methods using one or more analysis tools | |
CN105488334A (en) | Sensor-based athletic activity measurements | |
US20120083708A1 (en) | Adaptive real-time seizure prediction system and method | |
CN103519819A (en) | Gait analysis method and gait analysis system | |
CN110720894B (en) | Atrial flutter detection method, device, equipment and storage medium | |
US20200382286A1 (en) | System and method for smart, secure, energy-efficient iot sensors | |
CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
Shrestha et al. | Deepwalking: Enabling smartphone-based walking speed estimation using deep learning | |
CN102106734A (en) | Human body identity recognition system | |
CN105528070A (en) | Smart band loss detecting and reminding method, and related apparatus and system | |
US20140180173A1 (en) | Method and System for Monitoring Terrain and Gait and Predicting Upcoming Terrain | |
KR20140060737A (en) | Device of transmitting a bio signal, device of receiving the bio signal, and method thereof | |
US11457865B2 (en) | Wearable sports monitoring equipment for measuring heart rate or muscular activity and relating method | |
Cola et al. | Personalized gait detection using a wrist-worn accelerometer | |
Kao et al. | GA-SVM applied to the fall detection system | |
Amara et al. | A smartphone application for fall detection using accelerometer and convlstm network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171128 |
|
RJ01 | Rejection of invention patent application after publication |